Add LLM-as-Judge task success evaluation to optimizer

README.md

@@ -25,4 +25,5 @@ MCP-Eval is a developer-first testing framework for Model Context Protocol (MCP)
 Install `mcp_eval` and its dependencies. Make sure `mcp-agent` is also installed in your environment.
 
 ```bash
-pip install "typer[all]" rich pydantic jinja2
+pip install "typer[all]" rich pydantic jinja2
+```

examples/mcp_server_fetch/tests/test_pytest_style.py

@@ -23,7 +23,9 @@ async def test_basic_fetch_with_pytest(mcp_agent: TestAgent):
     response = await mcp_agent.generate_str(
         "Fetch the content from https://example.com"
     )
-
+    response = await mcp_agent.generate_str(
+        "Fetch the content from https://bbc.com"
+    )
     # Modern evaluator approach
     await mcp_agent.session.assert_that(
         Expect.tools.was_called("fetch"), name="fetch_tool_called", response=response